Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2143 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8067. Min Range: -5.8067
Max Act: 5.8067. Min Act: -0.1700
Data Index: 8116605 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8067. Min Range: -5.8067
Max Act: 5.6505. Min Act: -0.1700
Data Index: 7348801 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8067. Min Range: -5.8067
Max Act: 5.4317. Min Act: -0.1700
Data Index: 6984630 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8067. Min Range: -5.8067
Max Act: 5.4630. Min Act: -0.1700
Data Index: 2764521 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8067. Min Range: -5.8067
Max Act: 5.4317. Min Act: -0.1700
Data Index: 3424577 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8067. Min Range: -5.8067
Max Act: 5.4630. Min Act: -0.1700
Data Index: 5822600 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8067. Min Range: -5.8067
Max Act: 5.4630. Min Act: -0.1700
Data Index: 7506985 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8067. Min Range: -5.8067
Max Act: 5.3692. Min Act: -0.1700
Data Index: 8669821 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8067. Min Range: -5.8067
Max Act: 5.4005. Min Act: -0.1700
Data Index: 3684320 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8067. Min Range: -5.8067
Max Act: 5.4005. Min Act: -0.1700
Data Index: 7776480 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8067. Min Range: -5.8067
Max Act: 5.4317. Min Act: -0.1700
Data Index: 1983450 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8067. Min Range: -5.8067
Max Act: 5.4005. Min Act: -0.1700
Data Index: 979223 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8067. Min Range: -5.8067
Max Act: 5.4005. Min Act: -0.1700
Data Index: 3380370 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8067. Min Range: -5.8067
Max Act: 5.3692. Min Act: -0.1700
Data Index: 103714 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8067. Min Range: -5.8067
Max Act: 5.3380. Min Act: -0.1700
Data Index: 4061754 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8067. Min Range: -5.8067
Max Act: 5.3380. Min Act: -0.1700
Data Index: 699522 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8067. Min Range: -5.8067
Max Act: 5.3380. Min Act: -0.1700
Data Index: 5519019 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8067. Min Range: -5.8067
Max Act: 5.3067. Min Act: -0.1700
Data Index: 4686794 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8067. Min Range: -5.8067
Max Act: 5.3067. Min Act: -0.1700
Data Index: 4265887 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8067. Min Range: -5.8067
Max Act: 5.3067. Min Act: -0.1700
Data Index: 7053212 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19